Abstract
The detailed understanding of animal locomotion is an important part of biology, motion science and robotics. To analyze the motion, high-speed x-ray sequences of walking animals are recorded. The biological evaluation is based on anatomical key points in the images, and the goal is to find these landmarks automatically. Unfortunately, low contrast and occlusions in the images drastically complicate this task. As recently shown, Active Appearance Models (AAMs) can be successfully applied to this problem. However, obtaining reliable quantitative results is a tedious task, as the human error is unknown. In this work, we present the results of a large scale study which allows us to quantify both the tracking performance of humans as well as AAMs. Furthermore, we show that the AAM-based approach provides results which are comparable to those of human experts.
Similar content being viewed by others
References
S. M. Gatesy, “Guineafowl hind limb function. I: Cineradiographic analysis and speed effects,” J. Morphol. 240(2), 1097–4687 (1999).
S. M. Gatesy, D. B. Baier, F. A. Jenkins, and K. P. Dial, “Scientific rotoscoping: A morphology-based method of 3-d motion analysis and visualization,” Journal of Experimental Zoology Part A: Ecological Genetics and Physiology A 313(5), 244–261 (2010).
E. L. Brainerd, D. B. Baier, S. M. Gatesy, T. L. Hedrick, K. A. Metzger, S. L. Gilbert, and J. J. Crisco, “X-ray reconstruction of moving morphology (XROMM): Precision, accuracy and applications in comparative biomechanics research,” J. Exp. Zool. A 313A(5), 262–279 (2010).
M. Fischer and K. Lilje, Dogs in Motion, VDH, 2011.
B. K. P. Horn and B. G. Schunck, “Determining optical flow,” Artif. Intell. 17(1–3), 185–203 (1981).
S. Baker and I. Matthews, “Lucas-kanade 20 years on: A unifying framework,” Int. J. Comput. Vision 56(3), 221–255, 2004.
G. D. Hager and P. N. Belhumeur, “Efficient region tracking with parametric models of geometry and illumination,” IEEE T. Pattern Anal. 20(10), 1025–1039 (1998).
D. G. Lowe, “Distinctive image features from scale-invariant keypoints,” Int. J. Comput. Vision 60(2), 91–110 (2004).
D. Haase and J. Denzler, “Anatomical landmark tracking for the analysis of animal locomotion in X-ray videos using active appearance models,” in Proceedings of the 17th Scandinavian Conference on Image Analysis (SCIA 2011), ser. LNCS, Eds. by A. Heyden and F. Kahl (Springer, 2011), No. 6688, pp. 604–615.
T. F. Cootes, G. J. Edwards, and C. J. Taylor, “Active appearance models,” in Proceedings of the 5th European Conference on Computer Vision, ser. LNCS, Eds. by H. Burkhardt and B. Neumann (Springer, 1998), Vol. 1407, pp. 484–498.
G. J. Edwards, T. F. Cootes, and C. J. Taylor, “Face recognition using active appearance models,” in Proceedings of the 5th European Conference on Computer Vision, ser. LNCS, Eds. by H. Burkhardt and B. Neumann (Springer, 1998), Vol. 1407, pp. 581–595.
T. F. Cootes, G. J. Edwards, and C. J. Taylor, “Active appearance models,” IEEE T. Pattern Anal. 23(6), 681–685 (2001).
D. Haase, J. A. Nyakatura, and J. Denzler, “Multi-view active appearance models for the X-ray based analysis of avian bipedal locomotion,” in Proceedings of the 33rd DAGM Symposium (DAGM 2011), ser. LNCS, Eds. by R. Mester and M. Felsberg (Springer, 2011), No. 6835, pp. 11–20.
F. L. Bookstein, “Landmark methods for forms without landmarks: Morphometrics of group differences in outline shape,” Med. Image Anal. 1(3), 225–243 (1997).
I. Matthews and S. Baker, “Active appearance models revisited,” International Journal of Computer Vision 60(2), 135–164 (2004).
B. Lelieveldt, M. üzümcü, R. van der Geest, J. Reiber, and M. Sonka, “Multi-view active appearance models for consistent segmentation of multiple standard views,” International Congress Series 1256, 1141–1146 (2003).
E. Oost, G. Koning, M. Sonka, P. V. Oemrawsingh, J. H. C. Reiber, and B. P. F. Lelieveldt, “Automated contour detection in X-ray left ventricular angiograms using multiview active appearance models and dynamic programming,” IEEE T. Med. Imaging 25(9), 1158–1171 (2006).
M. B. Stegmann, “Active appearance models: theory, extensions and cases,” in Master’s Thesis (Technical University of Denmark, DTU, 2000).
D. Haase and J. Denzler, “Comparative evaluation of human and active appearance model based tracking performance of anatomical landmarks in locomotion analysis,” in Proceedings of the 8th Open German-Russian Workshop Pattern Recognition and Image Understanding (OGRW-8-2011), 2011, pp. 96–99.
Author information
Authors and Affiliations
Corresponding author
Additional information
The article is published in the original. This article uses the materials of the report submitted at the 8th Open German-Russian Workshop “Pattern Recognition and Image Understanding,” Nizhni Novgorod, November 21–26, 2011.
Daniel Haase Daniel Haase received the Diploma degree in computer science with honors from the Friedrich Schiller University of Jena, Germany, in April 2010. Currently, he is working towards his Ph.D. at the chair for computer vision at the University of Jena under the supervision of Joachim Denzler. His research interest include statistical modeling, 2D/3D landmark tracking, 3D reconstruction and machine learning.
Joachim Denzler Joachim Denzler, born April 16th 1967, earned the degrees “Diplom-Informatiker”, “Dr.-Ing.”, and “Habilitation”” from the University of Erlangen in the years 1992, 1997, and 2003, respectively. Currently, he holds a position of full professor for computer science and is head of the Chair for Computer Vision, Department of Mathematics and Computer Science, Friedrich Schiller University of Jena. His research interests comprise active computer vision, object recognition and tracking, 3D reconstruction, and plenoptic modeling, as well as computer vision for autonomous systems. He is author and coauthor of over 200 journal papers and technical articles. He is a member of the IEEE, IEEE computer society, DAGM, and GI. For his work on object tracking, plenoptic modeling, and active object recognition and state estimation, he was awarded the DAGM best paper awards in 1996, 1999, and 2001, respectively.
John A. Nyakatura received his Ph.D. in the field of Evolutionary Biology / Zoology under the supervision of Prof. Dr. Martin S. Fischer with the distinction of “summa cum laude” from the University of Jena in 2011. He is currently participating in several research projects concerned with the evolution and functional morphology of locomotor systems of vertebrates. His research is at the interface of anatomy and biomechanics and combines diverse experimental and classic anatomical approaches from an evolutionary perspective. In collaborations, his work bridges gaps to the fields of robotics, paleontology and computer vision.
Rights and permissions
About this article
Cite this article
Haase, D., Nyakatura, J.A. & Denzler, J. Comparative large-scale evaluation of human and active appearance model based tracking performance of anatomical landmarks in X-ray locomotion sequences. Pattern Recognit. Image Anal. 24, 86–92 (2014). https://doi.org/10.1134/S1054661814010222
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S1054661814010222